MétaCan
Menu
Back to cohort

Instrumental variables matter: towards causal inference using deep learning

2023· article· en· W4386738802 on OpenAlexaff
Kunhan Wu, Zihan Wang, Jingyi Zhao, Haodong Xu, Tongyang Hao, Wenzhi Lin

Bibliographic record

VenueJournal of Physics Conference Series · 2023
Typearticle
Languageen
FieldMathematics
TopicAdvanced Causal Inference Techniques
Canadian institutionsUniversity of TorontoUniversity of Alberta
Fundersnot available
KeywordsCausal inferenceInferenceArtificial intelligenceComputer scienceMachine learningInstrumental variableCasualArtificial neural networkCausal modelField (mathematics)Outcome (game theory)EconometricsMathematicsStatistics

Abstract

fetched live from OpenAlex

Abstract Causal inference requires knowing causal connections between treatment and outcome variables, and DeepIV, a causal inference framework, is the pioneer work to predict such connections by crossing deep learning with causal inference in applying instrumental variables(IVs) to deep neural network. DeepIV has been proved to be one of the best methods in this field theoretically, but how the framework performs on real-life problems still remains unclear. This paper provides an implementation of DeepIV, and use the framework to predict causal effect from people’s educational background on their annual income. DeepIV framework allows us to take advantage of neural network to estimate causal effect by adjusting loss function. To evaluate the performace of DeepIV in solving real-life problems, our experiment is based on real datasets. The result of our experiment shows that DeepIV’s ability to predict causal effect on real data is at least as good as those of other casual inference models’ whose reliability has been verified in practice. Meanwhile, DeepIV does not have obvious shortcoming in predicting outcomes compared with other supervised learning methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.040
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.010
Threshold uncertainty score0.053

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.040
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0020.003
Open science0.0020.003
Research integrity0.0010.005
Insufficient payload (model declined to judge)0.0070.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.131
GPT teacher head0.389
Teacher spread0.258 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Physics Conference SeriesSame topicAdvanced Causal Inference TechniquesFrench-language works237,207